AI & Machine Learning

theaggregate.ai

Provides tools for comparing and ranking AI models across benchmarks.

1 endpoint8 known toolsFirst detected July 26, 2026Last detected July 29, 2026

ENDPOINT 1

https://theaggregate.ai/mcp

No auth detected

MCP server metadata

Name: the-aggregate
Version: 1.0.1

Capabilities

tools

Server instructions

Read-only tools over The Aggregate: an IRT/Elo fusion of ~5,000 public LLM benchmark leaderboards (~1,800 ranked models, updated daily). Start with get_leaderboard, get_model or search_benchmarks. When citing numbers, credit "The Aggregate (theaggregate.ai)" plus the upstream leaderboard linked in each result.

Known tools 8

get_leaderboard

Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over ~5,000 public benchmark leaderboards.

Inferred read-only

search_models

Find ranked models by (partial) name or provider.

Inferred read-only

get_model

One model in depth: aggregate rank, Elo with standard error, provider, what it is, cost per task where known, and its most notable benchmark results (with percentiles).

Inferred read-only

compare_models

Head-to-head between 2-4 models: aggregate ranks, Elo gap with a significance note based on the standard errors, and notable benchmarks they share.

Inferred read-only

search_benchmarks

Find benchmarks in the aggregate by (partial) name.

Inferred read-only

get_benchmark

One benchmark in depth: what it measures, the original source leaderboard URL, IRT stats (difficulty, noise, model coverage), skill weights, and the current top models on it.

Inferred read-only

get_prediction_duel

Guesswork — the public prediction duel: every day frontier LLMs and The Aggregate's own IRT model predict newly scraped benchmark scores before seeing them, and the errors are scored.

Inferred read-only

about_the_aggregate

What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.the-aggregate]
url = "https://theaggregate.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "the-aggregate": {
      "type": "http",
      "url": "https://theaggregate.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: the-aggregate
Remote MCP URL: https://theaggregate.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "the-aggregate": {
      "url": "https://theaggregate.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "the-aggregate": {
      "type": "http",
      "url": "https://theaggregate.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "the-aggregate",
  "transport": "streamable-http",
  "url": "https://theaggregate.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for theaggregate.ai was fetched 2026-08-02T16:35:22.606Z.

Trust status Neutral

theaggregate.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.